Knowledge-enhanced Memory Model for Emotional Support Conversation

The prevalence of mental disorders has become a significant issue, leading to the increased focus on Emotional Support Conversation as an effective supplement for mental health support. Existing methods have achieved compelling results, however, they still face three challenges: 1) variability of emotions, 2) practicality of the response, and 3) intricate strategy modeling. To address these challenges, we propose a novel knowledge-enhanced Memory mODEl for emotional suppoRt coNversation (MODERN). Specifically, we first devise a knowledge-enriched dialogue context encoding to perceive the dynamic emotion change of different periods of the conversation for coherent user state modeling and select contextrelated concepts from ConceptNet for practical response generation. Thereafter, we implement a novel memory-enhanced strategy modeling module to model the semantic patterns behind the strategy categories. Extensive experiments on a widely used large-scale dataset verify the superiority of our model over cutting-edge baselines.

Introduction

Emotional Support Conversations (ESConv)

• Defination: It takes place between a help-seeker (user) and a supporter (dialogue model) in a multi-turn manner, aiming to provide support for those in need.
• Special Feature: It requires the dialogue model to employ a range of supportive strategies effectively.
• Two Aspects of Existing work:
  • Enhance the model’s comprehension of the contextual semantics in the conversations.
  • Predicting the dialogue strategy accurately and responding based on the predicted strategy categor.

Challenges

• Variability of emotions: user’s emotional state evolves subtly and constantly as the conversation goes.
• Practicality of the response: neural dialogue systems are inclined to make generic response in the absence of context-related concepts. (See above figure)
• Intricate strategy modeling: Dialogue strategy is hard to modeling as it is a highly complex concept encompassing various intricate linguistic features

Method

Knowledge-enriched Dialogue Context Encoding

• Change-aware Emotion Detection
• Context-related Concepts Reasoning and Selection

Memory-enhanced Strategy Modeling

• Strategy Pattern Extractor
• Strategy-specific Memory Bank
• Memory-enhanced Encoding